© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 9173
    Prev
    Next
    INDEX
    Explanations

    references to quests in role-playing games (RPGs) and their associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    496
    +0.14
    0.8%
    410
    +0.13
    0.7%
    322
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.14
    0.07
    440
    +0.13
    0.01
    322
    +0.13
    0.09
    Negative Logits
    »¿
    -3.84
    Ī
    -3.53
    ¬
    -3.50
    «
    -3.49
    ī
    -3.40
    Ļ
    -3.39
    Ķ
    -3.32
    ·
    -3.23
    ĩ
    -3.19
    ķ
    -3.13
    POSITIVE LOGITS
    s
    9.16
    sburg
    3.67
    smen
    3.56
    sz
    3.27
    shire
    3.21
    sar
    3.21
    som
    3.20
    es
    3.17
    sie
    3.15
    sen
    3.15
    Activations Density 1.703%

    No Known Activations